maze-l2rpn-2021-submission | power network challenge is a series

maze-l2rpn-2021-submission is a Python library. maze-l2rpn-2021-submission has no bugs, it has no vulnerabilities, it has build file available and it has low support. However maze-l2rpn-2021-submission has a Non-SPDX License. You can download it from GitHub.

The "Learning to run a power network" (L2RPN) challenge is a series of competitions organized by RTE, the French Transmition System Operator with the aim to test the potential of reinforcement learning (RL) to control electrical power transmission. The challenge is motivated by the fact that existing methods are not adequate for real-time network operations on short temporal horizons in a reasonable compute time. Also, power networks are facing a steadily growing share of renewable energy, requiring faster responses. This raises the need for highly robust and adaptive power grid controllers. In 2021, the L2RPN competition was held at the International Conference on Automated Planning and Scheduling (ICAPS). This repository contains the submission of enliteAI's RL-team which ranked 3rd on the official leaderboard (maze-rl). The code in this repository builds on our RL framework Maze. For a Maze-RL implementation of the winning solution from an early L2RPN challenge please refer to the gitbub repository or for a more extensive wrap up you can also check out our accompanying blog post.